|
|
State of the art speech features used during the Parkinson disease diagnosis
Bílý, Ondřej ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
This work deals with the diagnosis of Parkinson's disease by analyzing the speech signal. At the beginning of this work there is described speech signal production. The following is a description of the speech signal analysis, its preparation and subsequent feature extraction. Next there is described Parkinson's disease and change of the speech signal by this disability. The following describes the symptoms, which are used for the diagnosis of Parkinson's disease (FCR, VSA, VOT, etc.). Another part of the work deals with the selection and reduction symptoms using the learning algorithms (SVM, ANN, k-NN) and their subsequent evaluation. In the last part of the thesis is described a program to count symptoms. Further is described selection and the end evaluated all the result.
|
|
| |
|
|
Phonotactic framework of the Czech word and stress-group
Churaňová, Eliška ; Volín, Jan (advisor) ; Palková, Zdena (referee)
This master thesis provides a relatively detailed description of the consonant-vowel structure of standard spoken Czech. The first part covers approaches to and findings on the combinatorial system and distribution of sound units in speech; aspects of continuous speech segmentation into intonation phrases and stress groups, phonotactics of languages in general and Czech in particular, and speech rhythm are also addressed. Recordings of 12 professional speakers of Czech - comprising 6639 words and 5368 stress groups in total - have been used to create data sets that have enabled the author to describe CVCV structures of Czech words and stress groups. The results of this research present frequencies of words and stress groups and their relations to word-class dimension, frequencies of phones in words and stress groups; in this respect, both syllabic liquids and glottal stops have been taken into account. Further, the thesis includes an overview of the most frequent CVCV patterns in words and stress groups and their variability with regard to word classes. The final part focuses on how frequently consonants, vowels and their pairs and trios occur at different places within a unit. The results are continuously compared both between themselves and with the research that used the larger SYN2005 written...
|
|
| |
|
|
About Two Consonant Conflicts of Belief Functions
Daniel, M. ; Kratochvíl, Václav
General belief functions usually bear some internal conflict which comes mainly from disjoint focal elements. Analogously, there is often some conflict between two (or more) belief functions. After the recent observation of hidden conflicts (seminar CJS’17 [17]), appearing at belief functions with disjoint focal elements, importance of interest in conflict of belief functions has increased. This theoretical contribution introduces a new approach to conflicts (of belief functions). Conflicts are considered independently of any combination rule and of any distance measure. Consonant conflicts are based on consonant approximations of belief functions in general; two special cases of the consonant approach based on consonant inverse pignistic and consonant inverse plausibility transforms are discussed. Basic properties of the newly defined conflicts are presented, analyzed and briefly compared with our original approaches to conflict (combinational conflict, plausibility conflict and comparative conflict), with the recent conflict based on non-conflicting parts, as well as with W. Liu’s degree of conflict.
|
|
| |
|
|
Pronunciation of consonantal clusters in the Czech speech of Spanish speakers
Pugachova, Kateryna ; Veroňková, Jitka (advisor) ; Škodová, Svatava (referee)
The topic of this thesis belongs to the area of L2 acquisition. It focuses on the Czech as a second/foreign language for native Spanish speakers, specifically on their pronunciation of selected consonantal clusters in comparison with the Czech orthoepic norm. The theoretical part summarizes the problems learning the pronunciation of second/foreign language and describes phonetic systems, syllable structure and specific combinatorial properties of sounds in Czech and Spanish. The practical part describes the research for which thirteen Spanish speakers from different countries and with different length of stay in the Czech Republic were recorded. For the purpose of the research a special text containing the selected consonantal clusters in initial, medial and final position of the word was compiled. Words were examined with a perceptive analysis and the results were processed according to established criteria.
|
|
|
Consonantal and vocalic differences in Czech English with reduced and enhanced foreignness
Pojarová, Veronika ; Volín, Jan (advisor) ; Weingartová, Lenka (referee)
The objective of this thesis is to identify those features of the Czech accent in English that are the most salient in the perception of the Czech listener and that may disturb the communication process. The purpose of the introductory chapter is to familiarize the reader with the subject of the foreign accent, to provide a brief summary of the current state of research and to introduce a series of empirical studies. The research part of the thesis analyzes the individual realizations of the selected speech sounds /θ, ð, ŋ, r, w, æ, ɜː/ and ventures to draw meaningful conclusions from the results. The material analyzed consists of a total of 3568 speech sound tokens, recorded by 9 male and 19 female speakers. Each respondent produced two recordings, one in the British standard mode and another where the speaker imitated the Czech foreign accent. The 3568 tokens were individually rated and the two modes were then compared for each speaker. The results showed /r/ to be favoured by the largest number of speakers as an indicator of the Czech accent, while /θ, ð, ŋ/ often had the same rating in both modes. However, additional factors such as speaker proficiency and number of tokens from individual speech sounds must be taken into consideration before any final conclusions can be drawn from the raw data....
|
|
|
Phonotactic framework of the Czech word and stress-group
Churaňová, Eliška ; Volín, Jan (advisor) ; Palková, Zdena (referee)
This master thesis provides a relatively detailed description of the consonant-vowel structure of standard spoken Czech. The first part covers approaches to and findings on the combinatorial system and distribution of sound units in speech; aspects of continuous speech segmentation into intonation phrases and stress groups, phonotactics of languages in general and Czech in particular, and speech rhythm are also addressed. Recordings of 12 professional speakers of Czech - comprising 6639 words and 5368 stress groups in total - have been used to create data sets that have enabled the author to describe CVCV structures of Czech words and stress groups. The results of this research present frequencies of words and stress groups and their relations to word-class dimension, frequencies of phones in words and stress groups; in this respect, both syllabic liquids and glottal stops have been taken into account. Further, the thesis includes an overview of the most frequent CVCV patterns in words and stress groups and their variability with regard to word classes. The final part focuses on how frequently consonants, vowels and their pairs and trios occur at different places within a unit. The results are continuously compared both between themselves and with the research that used the larger SYN2005 written...
|
|
|
State of the art speech features used during the Parkinson disease diagnosis
Bílý, Ondřej ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
This work deals with the diagnosis of Parkinson's disease by analyzing the speech signal. At the beginning of this work there is described speech signal production. The following is a description of the speech signal analysis, its preparation and subsequent feature extraction. Next there is described Parkinson's disease and change of the speech signal by this disability. The following describes the symptoms, which are used for the diagnosis of Parkinson's disease (FCR, VSA, VOT, etc.). Another part of the work deals with the selection and reduction symptoms using the learning algorithms (SVM, ANN, k-NN) and their subsequent evaluation. In the last part of the thesis is described a program to count symptoms. Further is described selection and the end evaluated all the result.
|
guest ::
